A couple of 20-year-old developers make $500,000 a month promising to help men to stop watching porn, but exposed their private porn watching habits.

  • hammertime@lemmy.org
    link
    fedilink
    arrow-up
    18
    arrow-down
    86
    ·
    14時間前

    Once you learn how to CODE, you’ll realize how dumb it is to blame everything on AI.

      • hammertime@lemmy.org
        link
        fedilink
        arrow-up
        4
        arrow-down
        64
        ·
        13時間前

        Right. It’s called using AI. Not letting your vibes make decisions. Glad you agree.

        • bassomitron@lemmy.world
          link
          fedilink
          English
          arrow-up
          31
          arrow-down
          2
          ·
          13時間前

          The vibe coding thing is a meme that originated in what devs at Microsoft said about how they develop while using AI, if I recall correctly. So vibe-coding has become synonymous with using AI to write the majority of your code.

            • bassomitron@lemmy.world
              link
              fedilink
              English
              arrow-up
              2
              ·
              edit-2
              2時間前

              I’m confused why you linked a Wiki article that reiterates almost exactly what I said? Think the only difference is that it was originally coined by the dude who helped start OpenAI.

              And no, most major dev teams aren’t “vibe coding,” but that’s where it becomes a meme. People use it as an insult as well for shit code.

              Regardless, your main argument here that “real devs aren’t vibe coding,” is irrelevant, as the people in the original article don’t seem to be competent devs. It’s very possible they used AI-slop code; but, even if they didn’t, they did a piss-poor job so it might as well be insulted as such.

            • Sonicdemon86@lemmy.world
              link
              fedilink
              English
              arrow-up
              15
              ·
              12時間前

              “The software developer describes a project or task in a prompt to a large language model (LLM), which generates source code automatically. Vibe coding typically involves accepting AI-generated code without reviewing it, instead relying on results and follow-up prompts to guide changes.” A.I. written code. Software devs normally check the code for bugs not just accepting whatever code is thrown at them with no checks. It is why real developers are making money fixing the A.I. bullshit code.

              • hammertime@lemmy.org
                link
                fedilink
                arrow-up
                3
                arrow-down
                35
                ·
                11時間前

                Right. Actual vibe coding is rare in real development. Especially large companies. You’d know this if you were a developer. But it’s much more fun to complain about AI with such… “confidence.”

                • python@lemmy.world
                  link
                  fedilink
                  arrow-up
                  13
                  arrow-down
                  1
                  ·
                  9時間前

                  lol you wish. You don’t know how many vibecoded bullshit PRs I have to review on a daily basis. AI is undeniably making developers worse.

                  • hammertime@lemmy.org
                    link
                    fedilink
                    arrow-up
                    2
                    arrow-down
                    19
                    ·
                    9時間前

                    That’s because your developers don’t give a shit. It’s not because they’re worse! It’s because they’re just waiting to get laid off. Most of them probably want to get laid off. And if you are reviewing PR‘s and you can’t control them using AI, you’re part of the problem.

    • Jo Miran@lemmy.ml
      link
      fedilink
      arrow-up
      22
      arrow-down
      1
      ·
      edit-2
      14時間前

      One of my biggest gripes with coding AI like Claude is how desperately polite and flattering they are. I wish there was a way to feed it hand written code to analyze for bugs and security flaws, then have the AI relentlessly roast your shitty code.

      "LMFAO, you dumb b!tch! Are you trying to get hacked and sued, by <insert dumb shit here> or are you just that stupid? Here are a few steps you can take to fix your shit code and have it adhere to standard coding practices. "

        • 9488fcea02a9@sh.itjust.works
          link
          fedilink
          arrow-up
          3
          arrow-down
          1
          ·
          11時間前

          So i was reading a thread from the linux kernel mailing list where linus pointed out someone’s coding mistake and why it would lead to a bug…

          So i fed the patch email into google gemini pro, and it spotted the same bug as linus

          I thought that was interesting.

      • StarryPhoenix97@lemmy.world
        link
        fedilink
        arrow-up
        5
        ·
        edit-2
        13時間前

        Hey ChatGPT, respond to all of my inquiries like my toxic abusive uncle. The more vicious the response the better. Withhold praise. Pretend it’s opposite day and give me your best compliments in the form of the life-long truama that I have come to associate with authority figures.

        Here’s my code. What do you think?

      • sp3ctr4l@lemmy.dbzer0.com
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        1
        ·
        edit-2
        9時間前

        I figured out a way to do this, via Alpaca.

        In Alpaca you can set an LLM with a persistent prompt.

        Basically, I just told the thing hey, you’re too sycophantic, often needlessly verbose, and often overly confident… can you generate a prompt for yourself to address those issues?

        Roughly 30 minutes of trial and error along those lines later, now its quite matter of fact, and is at least more likely to tell me when it is aware it is making an assumption, and ask me for clarification or if i can give it more context, and it doesn’t do the kind of weird, intro and outro paragraphs where it basically just reassures you that your ideas are wonderful and you are valid and i just think the things you say are so interesting!

        Then, you feed it a script, ask it do a sanity check, and it will generally go through and identify strenghts and weakness of the code, at least as it perceives such.


        Beyond that, Alpaca recently introduced a … character system, that is ostensibly tailored toward making specific kinds of conversational chat bots… but it also introduced a kind of ‘dictionary’ system, where you can give it a kind of additional permanent reference knowledge, to associate with certain terms.

        I have not tried this yet, but, I’d be willing to be that you could say, jam that with a bunch of examples of syntax and methods from a particular language or library… and my guess would be that you could thus tailor a ‘character’ that is more up to date or specific to some domain.

        So… you could give it the main prompt of something like “You are a tsuntsun senior programmer who has nothing but contempt for any coding mistakes, and you pride yourself on coming up with entirely novel insults for each inadequacy you notice.”

        … And then give it a ‘dictionary’ that pertains to syntax, methods, perhaps even broader concepts…

        And that might actually produce your desired vicious asshole senior programmer persona.

        Of course, this is not going to work for like, an entire massive codebase, unless you’re the one stockpiling all my the RAM.

        But for smaller projects or just single scripts… it might kind of work.

      • AlphaOmega@lemmy.world
        link
        fedilink
        English
        arrow-up
        2
        arrow-down
        1
        ·
        12時間前

        You can give it rules.

        I work with Gemini a lot and I told it to cut all the polite crap out and just give the facts I need.

        • frongt@lemmy.zip
          link
          fedilink
          arrow-up
          3
          arrow-down
          1
          ·
          12時間前

          On the rare occasion I use LLMs, I just wish they would respect my request for a list of like twenty bullets and nothing else, instead I get two paragraphs of bs and four bullets.

      • hammertime@lemmy.org
        link
        fedilink
        arrow-up
        2
        arrow-down
        5
        ·
        13時間前

        I don’t think it will ever cuss at you, but your can have it be more critical. It say to me all the time, “this or probably a bad idea, before I do this, consider this alternative” (paraphrasing)